Robust Iris Segmentation on Uncalibrated Noisy Images Using Mathematical Morphology

Miguel Ángel Luengo-Oroz (1, 2) , Emmanuel Faure (2, 3) , Jesus Angulo (4)

1 CIBER-BBN - Biomedical Image Technologies, Biomedical Research Center
2 ISC-PIF - Institut des Systèmes Complexes - Paris Ile-de-France
3 CREA - Centre de recherche en épistémologie appliquée
4 CMM - Centre de Morphologie Mathématique

This paper proposes a new approach for fast iris segmentation that relies on the closed nested structures of iris anatomy (the sclera is brighter than the iris, and the iris is brighter than the pupil) and on its polar symmetry. The described method applies mathematical morphology for polar/radial-invariant image filtering and for circular segmentation using shortest paths from generalized grey-level distances. The proposed algorithm obtained good results on the NICE-I contest and showed a very robust behavior, especially when dealing with half-closed eyes, different skin colours/illumination or subjects wearing glasses. © 2009 Elsevier B.V. All rights reserved.

Mots clés: Grey-level generalized distance; Iris segmentation; Non-cooperative iris biometry; Spatially variant mathematical morphology

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Imagerie médicale

Miguel Ángel Luengo-Oroz, Emmanuel Faure, Jesus Angulo. Robust Iris Segmentation on Uncalibrated Noisy Images Using Mathematical Morphology. Image and Vision Computing, 2010, 28 (2), pp.278-284. ⟨10.1016/j.imavis.2009.04.018⟩. ⟨hal-00836060⟩